wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix for Deepgram settings not merging

Browse Source
This commit is contained in:
Kwindla Hultman Kramer
2024-10-11 21:07:39 -07:00
parent 66a76af341
commit 53451899a7
2 changed files with 21 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/foundational/13b-deepgram-transcription.py
View File

@@ -14,7 +14,7 @@ from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.deepgram import DeepgramSTTService from pipecat.services.deepgram import DeepgramSTTService, LiveOptions, Language
from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.transports.services.daily import DailyParams, DailyTransport
from runner import configure from runner import configure
@@ -45,7 +45,10 @@ async def main():
room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True) room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
) )
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
# live_options=LiveOptions(language=Language.FR),
)
tl = TranscriptionLogger() tl = TranscriptionLogger()

23
src/pipecat/services/deepgram.py
View File

@@ -35,6 +35,7 @@ try:
LiveResultResponse, LiveResultResponse,
LiveTranscriptionEvents, LiveTranscriptionEvents,
SpeakOptions, SpeakOptions,
logging,
) )
except ModuleNotFoundError as e: except ModuleNotFoundError as e:
logger.error(f"Exception: {e}") logger.error(f"Exception: {e}")
@@ -118,7 +119,11 @@ class DeepgramSTTService(STTService):
*, *,
api_key: str, api_key: str,
url: str = "", url: str = "",
live_options: LiveOptions = LiveOptions( live_options: LiveOptions = None,
**kwargs,
):
super().__init__(**kwargs)
default_options = LiveOptions(
encoding="linear16", encoding="linear16",
language=Language.EN, language=Language.EN,
model="nova-2-conversationalai", model="nova-2-conversationalai",
@@ -129,15 +134,19 @@ class DeepgramSTTService(STTService):
punctuate=True, punctuate=True,
profanity_filter=True, profanity_filter=True,
vad_events=False, vad_events=False,
), )
**kwargs,
):
super().__init__(**kwargs)
self._settings = vars(live_options) merged_options = default_options
if live_options:
merged_options = LiveOptions(**{**default_options.to_dict(), **live_options.to_dict()})
self._settings = merged_options
self._client = DeepgramClient( self._client = DeepgramClient(
api_key, config=DeepgramClientOptions(url=url, options={"keepalive": "true"}) api_key,
config=DeepgramClientOptions(
url=url,
options={"keepalive": "true"}, # verbose=logging.DEBUG
),
) )
self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1") self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1")
self._connection.on(LiveTranscriptionEvents.Transcript, self._on_message) self._connection.on(LiveTranscriptionEvents.Transcript, self._on_message)